Generalized gradient emphasis learning for off-policy evaluation and control with function approximation.
Jiaqing CaoQuan LiuLan WuQiming FuShan ZhongPublished in: Neural Comput. Appl. (2023)
Keyphrases
- function approximation
- reinforcement learning
- td learning
- policy evaluation
- temporal difference
- learning tasks
- policy gradient
- temporal difference methods
- function approximators
- learning process
- model free
- learning algorithm
- least squares
- control system
- evaluation function
- dynamic programming
- radial basis function
- action selection
- supervised learning
- decision trees
- machine learning